Materials Intelligence

Integrating first-principles simulation and machine learning for materials discovery

...


Hi, I'm Andrij Vasylenko.

I am a Research Associate in the Department of Chemistry at the University of Liverpool.
My work explores how atomic structure and chemical composition determine material properties. By combining physics-based simulation and data-driven modelling, I aim to accelerate the discovery of functional materials for energy and sustainability applications.
My research has been shaped by collaborations with physicists and chemists at the Universities of Warwick and Cambridge, and by my Marie Skłodowska-Curie Fellowship at Adam Mickiewicz University, where I completed a PhD in Physics.

...

AI for Materials

Learning how atoms combine from historical data provides insight into which elemental combinations are synthetically accessible and functionally promising. To capture these relationships, I developed a variational autoencoder for unsupervised learning of compositional and structural patterns in chemical data. I further designed a Bayesian optimisation framework that accelerates targeted exploration of compositional space in combination with DFT-based crystal structure prediction. In collaboration with experimental groups, these approaches have led to the discovery of new functional materials.

Selected Publications:
A. Vasylenko et. al, Digital Discovery 4, 477 (2025)
G. Han, A. Vasylenko et. al, Science 383, 6684 (2024)
A. Vasylenko et. al, The Journal of Chemical Physics 160, 5 (2024)
A. Vasylenko et. al, npj Computational Materials 9, 164 (2023)
A. Vasylenko et. al, Nature Communications 12, 5561 (2021)

View projects

...

Quantum Mechanics for Materials

Quantum-mechanical methods, such as density functional theory (DFT) and beyond-DFT approaches, remain the benchmark for accuracy in atomistic materials modelling. While developing computationally efficient algorithmic alternatives — including data-driven and machine-learning models trained on synthetic data — I employ QM-based simulations to study materials properties with experimental validation. These include thermodynamic and chemical stability, crystal-structure prediction, electronic structure, and transport phenomena.

Selected Publications:
A. Pshyk, A. Vasylenko et. al, Materials & Design 219 (2022)
G. Han, A. Vasylenko et. al, JACS 143, 18216 (2021)
A. Vasylenko et. al, ACS Nano 12, 6023 (2018)
A. Vasylenko et. al, Phys. Rev B 95, 121408(R) (2017)

Software and Tools

Computational tools that I develop find their application in the fields far beyond Materials Science: E.g., in detection of anomalies and outliers in data, in general, as a part of the pyod library

View projects

CV